IDIADA optimizes AIDA chatbot interaction routing using Amazon Bedrock classifiers
As AIDA's user interactions grew more complex over time—from simple queries to document translations, service requests, and specialized inquiries—a coherent system was needed to categorize those interactions and route each one to a more specialized pipeline.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · User submits request to AIDA
Users submit queries to AIDA ranging from simple questions to complex tasks such as document translations, service requests, and specialized inquiries.
Tools used
Amazon BedrockClaude 3 SonnetLangChainBoto3Amazon Titan Text Embeddings G1Amazon S3Coherescikit-learnKerasTensorFlowPython
Outcome
SVM and ANN models using Cohere's multilingual embeddings achieved the best balance of performance and speed, with the SVM reaching F1 scores of 0.99, 0.80, and 0.93 across the three classes at a runtime of approximately 0.3 seconds—far faster than the LLM's 1.2 seconds and LLM with examples' 18 seconds.
What failed first
LLM-based classification with examples improved accuracy but faced critical scalability limits: the volume of examples required caused infrastructure overflow, quota issues with Amazon Bedrock, and runtimes up to 18 seconds—unacceptable for user experience.